All integrations

Integration · Direct HTTP (curl, custom agents)

Use GSC PAP without an MCP client

3 steps · about 4 minutes

If your AI client doesn't support MCP yet, or you're building a custom agent, you can talk to GSC PAP directly over HTTP. The MCP protocol is just JSON-RPC over Streamable HTTP, any HTTP client can speak it.

This guide shows the raw shape: handshake, list tools, call a tool. Use it for testing, scripting, or as the basis for a custom integration.

Steps

  1. 1

    Sign in to GSC PAP and copy your token

    Visit gscpap.com → Sign in with Google → grant Search Console + GA4 scopes → copy the bearer token from the connect page.

  2. 2

    Initialize the MCP session

    POST a JSON-RPC `initialize` request. The server returns its capabilities. The same Authorization header carries your bearer on every subsequent request.

    shell
    curl -X POST https://mcp.gscpap.com/mcp \
      -H "Authorization: Bearer YOUR_TOKEN_HERE" \
      -H "Content-Type: application/json" \
      -H "Accept: application/json, text/event-stream" \
      -d '{
        "jsonrpc": "2.0",
        "id": 1,
        "method": "initialize",
        "params": {
          "protocolVersion": "2025-06-18",
          "capabilities": {},
          "clientInfo": {"name": "curl", "version": "1.0"}
        }
      }'
  3. 3

    List + call tools

    After initialize succeeds you can call `tools/list` to discover the 30 available tools, then `tools/call` to invoke any of them by name. Sample call to list_sites, replace `tools/call` payload with any other tool from the list.

    shell
    curl -X POST https://mcp.gscpap.com/mcp \
      -H "Authorization: Bearer YOUR_TOKEN_HERE" \
      -H "Content-Type: application/json" \
      -H "Accept: application/json, text/event-stream" \
      -d '{
        "jsonrpc": "2.0",
        "id": 2,
        "method": "tools/call",
        "params": {
          "name": "list_sites",
          "arguments": {}
        }
      }'

Common gotchas

  • ·GSC PAP runs `stateless_http: true` mode, every request is independent. You don't need to keep a session id across calls; each request just carries the bearer.
  • ·Rate limits apply per-token: 30 requests/minute, 500/hour. The server returns 429 with a Retry-After header when you exceed them. Live usage at app.gscpap.com/account.
  • ·For Python agents, the official `mcp` package (pip install mcp) wraps all of this for you, preferred over raw curl unless you're scripting one-off shell pipelines.
  • ·Bearer tokens are logged on the client side if you use `curl -v` for debugging. Strip the Authorization line from any output you share for support.

Other integrations

All integrations

Claude Desktop

Wire your Google Search Console to Claude Desktop in five minutes. Step-by-step instructions for macOS and Windows, with the exact JSON config to paste.

5 steps · 5 min read

Cursor

Use Search Console data inside Cursor's AI chat. Five-step setup, single JSON config, works in any project.

5 steps · 5 min read

Claude Code

Two-line CLI setup for Claude Code, Anthropic's terminal-based agent. User-scope means it works in every project automatically.

3 steps · 3 min read

Codex CLI (OpenAI)

Connect Google Search Console, GA4, and PageSpeed Insights to OpenAI's Codex CLI in three minutes. Bearer-token auth via env var, works in both the CLI and the Codex IDE extension.

4 steps · 4 min read

VS Code (GitHub Copilot)

Wire your Google Search Console + GA4 + PageSpeed data into VS Code's GitHub Copilot agent mode in five minutes. Native MCP support since VS Code 1.101.

5 steps · 5 min read

Gemini CLI (Google)

Connect Search Console, GA4, and PageSpeed data to Google's Gemini CLI agent. Streamable HTTP MCP support, bearer-token auth, works inside Gemini's 1M-token context window.

4 steps · 4 min read

Windsurf IDE

Plug Search Console, GA4, and PageSpeed data into Windsurf's Cascade agent in five minutes. Bearer-token auth, works with both local and remote agent runs.

4 steps · 5 min read

Zed Editor

Wire Search Console, GA4, and PageSpeed Insights into Zed's AI assistant. Native MCP context-server support via settings.json.

3 steps · 4 min read

JetBrains IDEs

Wire Search Console, GA4, and PageSpeed into IntelliJ, PyCharm, WebStorm, GoLand, any JetBrains IDE 2025.2 or newer. Native MCP support via the AI Assistant settings.

4 steps · 5 min read

Continue (extension)

Continue is a popular open-source AI coding assistant with VS Code and JetBrains extensions. Add GSC PAP as an MCP server in three minutes via its config.json.

3 steps · 3 min read

Claude.ai (browser)

Connect Search Console, GA4, and PageSpeed to Claude.ai in your browser through the Connectors panel. OAuth flow, no token to copy, no config file to edit. Works for free and paid Claude plans.

3 steps · 3 min read

Done. Your AI client now has access to your Search Console data.

Got stuck? Email support@gscpap.com with the error and we will revise the guide.